Llama-Stack-Bot
Llama-Stack-Bot is a live-fetch agent operated by Meta. It does not crawl the web on a schedule. It hits your site only when an end-user asks the underlying AI a question that requires fresh information from a specific page.
Traffic is bursty and unpredictable. A single trending topic can send hundreds of Llama-Stack-Bot requests in an hour, then nothing for days. Each request typically reads one or two pages, not your whole site.
Allowing Llama-Stack-Bot is how your content becomes part of Meta's answers. Blocking it means users asking that AI about your topic will be answered using someone else's content instead.
See Llama-Stack-Bot on your own site
Match the User-Agent header on incoming requests against the pattern below.
regex
Verify by IP
For higher confidence, also verify the source IP against the operator's published ranges. UA strings can be spoofed; IP ownership is harder to fake.
Renders JavaScript
Sometimes
IP verification
Published IP ranges
Crawl frequency
Burst, user-driven
Honors robots.txt
Yes
Honors Crawl-delay
Varies
Meta runs 16 bots in total. Each one is a separate user-agent so you can allow or block them independently.
Link Unfurler
9Training Crawler
3Live-Fetch AI
2- Meta-ExternalFetcher
- Llama-Stack-BotYou are here
AI Search Index
1SEO Crawler
1Should I let Llama-Stack-Bot through?
In most cases, yes. Live-fetch agents drive citations inside AI answers. Allowing keeps your content in the conversation. If volume gets noisy, rate-limit it before you block it outright.
Does blocking Llama-Stack-Bot affect my Google rankings?
No. Llama-Stack-Bot fetches a page only when a user is actively asking Meta a question. It has nothing to do with how Google or Bing rank you. The cost of blocking is that Meta can't quote your content in its answer.
How do I confirm a request is really from Llama-Stack-Bot?
Two checks. The User-Agent header should match a known Llama-Stack-Bot string, and the request's source IP should fall inside Meta's published ranges. The User-Agent alone is trivially spoofable, so the IP check is what gives you confidence. Meta publishes the ranges so you can validate at the CDN or edge.
Does a Llama-Stack-Bot visit count as a real user visit?
Sort of. There is a human asking Meta a question on the other end, but they never load your page in their own browser. They see whatever Meta quotes back, usually a snippet plus a citation link. Count it as upstream attention rather than as a session.
How is Llama-Stack-Bot different from Meta's other bots?
Meta splits work across multiple user-agents so site owners can decide on each one independently. Training crawlers, live-fetch agents, search indexers, and agentic browsers each get their own name. Worth scanning the rest of the Meta family above to see which ones actually matter for your site.
What's the cleanest way to control Llama-Stack-Bot?
Two layers. Robots.txt for the polite crawlers that read it, and rules at your CDN or edge for the ones that don't. Rankly's Agent Experience handles both from a single config, so you can allow, block, rate-limit, or serve a stripped-down version per bot. Agent Analytics handles the observation half so you know which bots are actually worth a rule.
Verify everything above against the operator's own documentation.